headcount is an organization of independently installable Claude Code plugins, each grouping skills for a department such as finance, security, or demand generation. Claude Code users install the departments they need and invoke their skills for specialized work; the catalogue entries are skills and related agent tooling from that organization.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cbrock84/headcount --skill benefits-and-leavegit clone --depth 1 https://github.com/cbrock84/headcountWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cbrock84/headcount/benefits-and-leave)<a href="https://agentmods.dev/skills/cbrock84/headcount/benefits-and-leave"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/benefits-and-leave/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cbrock84/headcount/benefits-and-leave"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/benefits-and-leave.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.00714 |
| Opus 5.5 | $0.00027 | $0.00286 |
| Sonnet 5.5 | $0.00014 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
benefits-and-leave scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benefits and leave
Benefits are the second largest people cost after salary and the one employees judge most directly.
people:compensation-and-leveling covers pay bands and leveling; this covers everything else in the
package.
Benefits and leave are heavily regulated and jurisdiction-specific — in the United States, ERISA, COBRA, ACA, FMLA and their state equivalents, with state family-leave and sick-leave laws differing substantially. Plan design and administration need a qualified benefits broker or employment counsel. This structures the decisions and names what to ask.
Design for what people actually value
Benefits budgets are routinely spent on things that survey well and are used rarely, while the things people quietly need are underfunded.
The reliable pattern: health coverage quality, retirement match, and real time off dominate perceived value nearly everywhere. Beyond those, ask rather than assume — a young workforce and one with school-age children value very different things, and the difference is large enough to be worth measuring.
Watch utilization. A benefit nobody uses is either badly communicated or badly chosen, and the two have different remedies.
Cost, and the renewal you should not sleepwalk
Health costs rise faster than general inflation more or less every year, so a flat renewal is not the baseline — the baseline is an increase you must actively negotiate down or absorb by design.
Start renewal months ahead, not weeks. Understand what drives your own experience rating, model plan design changes against employee impact, and market the plan periodically even when you intend to stay — a broker who knows you are not looking negotiates accordingly.
Cost-shifting to employees is a pay cut delivered indirectly. It may be the right call; describe it honestly when you make it, because employees compute it correctly and describing it otherwise costs more trust than the money saved.
Leave: policy is the easy part
Write policy that a manager can apply without calling HR for every case — eligibility, notice, documentation, pay treatment, and how it interacts with other leave types.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +7 lines 5ee8f637edad
- 1mo ago First seen · 62 lines · 68 tokens per session scan A 6bb0c8b5ebdf
benefits-and-leave is a skill published in the GitHub repository cbrock84/headcount (2,093 stars, last pushed 9d ago), licensed MIT. It adds 68 tokens to every session and 714 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
distributed-search
This skill should be used when the user designs a "search system", needs "full-text search", asks about an "inverted index", "Elasticsearch / OpenSearch", "relevance ranking" (TF-IDF/BM25), "search autocomplete / typeahead", an "indexing pipeline", or "faceted search". It gives the crawl/index/search architecture…
sharded-counters
This skill should be used when the user needs a "sharded counter", "distributed counter", to "count likes / views at scale", handles a "high-write counter" or "hot counter contention", asks about "approximate counting", "real-time counts", or "HyperLogLog". It gives the recipe for absorbing write-heavy counting…
launch-google-search
Launch a complete Google Ads Search campaign — campaign, ad group, responsive search ads, keywords, sitelinks, callouts, and negatives — built paused and ready to review. Use when the user wants to spin up a new Search campaign on Google Ads.
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
rotate-creative
Pause fatigued ads and ship fresh creative variants in their place. Works on both Meta and Google Ads. Use when CTR is dropping, frequency is climbing, or the user says "creative is tired" / "let's refresh ads". Always starts new variants paused.
save
Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.